{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5262519121170044, "min": 0.5225420594215393, "max": 1.4878922700881958, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15762.296875, "min": 15667.900390625, "max": 45136.69921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4445922374725342, "min": -0.10023865848779678, "max": 0.5665634870529175, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 118.26153564453125, "min": -24.157516479492188, "max": 156.93807983398438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011070070788264275, "min": -0.010128838010132313, "max": 0.23419231176376343, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.944638729095459, "min": -2.704399824142456, "max": 56.206153869628906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06752148332140809, "min": 0.06442563916915729, "max": 0.07403518965639662, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9453007664997132, "min": 0.49547166649309715, "max": 1.0636769941775128, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014057257705731204, "min": 0.0009316632641662048, "max": 0.015581022142820682, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19680160788023687, "min": 0.008701211273577866, "max": 0.2316412297077477, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.448904659921426e-06, "min": 7.448904659921426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010428466523889997, "min": 0.00010428466523889997, "max": 0.0035081849306051, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024829357142857, "min": 0.1024829357142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347610999999998, "min": 1.3691136000000002, "max": 2.5693949000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025804527785714277, "min": 0.00025804527785714277, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003612633889999999, "min": 0.003612633889999999, "max": 0.11696255050999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007796562276780605, "min": 0.007796562276780605, "max": 0.36631712317466736, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10915187001228333, "min": 0.10915187001228333, "max": 2.5642199516296387, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 418.5, "min": 318.5376344086022, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30132.0, "min": 15984.0, "max": 33352.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3590844820292902, "min": -1.0000000521540642, "max": 1.6599462190142242, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 96.49499822407961, "min": -32.000001668930054, "max": 154.37499836832285, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3590844820292902, "min": -1.0000000521540642, "max": 1.6599462190142242, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 96.49499822407961, "min": -32.000001668930054, "max": 154.37499836832285, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03394484631618826, "min": 0.026193514618063747, "max": 7.271100605838001, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4100840884493664, "min": 2.344536343298387, "max": 116.33760969340801, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710871132", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710873391" }, "total": 2259.6114234789998, "count": 1, "self": 0.4887822480000068, "children": { "run_training.setup": { "total": 0.0502046369999789, "count": 1, "self": 0.0502046369999789 }, "TrainerController.start_learning": { "total": 2259.072436594, "count": 1, "self": 1.4859087300892497, "children": { "TrainerController._reset_env": { "total": 2.08895148900001, "count": 1, "self": 2.08895148900001 }, "TrainerController.advance": { "total": 2255.402366883911, "count": 63729, "self": 1.544523137862143, "children": { "env_step": { "total": 1629.9095483539961, "count": 63729, "self": 1490.4178479539578, "children": { "SubprocessEnvManager._take_step": { "total": 138.54076042106112, "count": 63729, "self": 4.943549150067156, "children": { "TorchPolicy.evaluate": { "total": 133.59721127099397, "count": 62561, "self": 133.59721127099397 } } }, "workers": { "total": 0.9509399789772033, "count": 63729, "self": 0.0, "children": { "worker_root": { "total": 2253.6122201120033, "count": 63729, "is_parallel": true, "self": 892.2448907209678, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002235000999917247, "count": 1, "is_parallel": true, "self": 0.0006491789999927278, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015858219999245193, "count": 8, "is_parallel": true, "self": 0.0015858219999245193 } } }, "UnityEnvironment.step": { "total": 0.05140369099990494, "count": 1, "is_parallel": true, "self": 0.0006337400002394133, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000531449999925826, "count": 1, "is_parallel": true, "self": 0.000531449999925826 }, "communicator.exchange": { "total": 0.04849321299980147, "count": 1, "is_parallel": true, "self": 0.04849321299980147 }, "steps_from_proto": { "total": 0.0017452879999382276, "count": 1, "is_parallel": true, "self": 0.00036582300003829005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013794649998999375, "count": 8, "is_parallel": true, "self": 0.0013794649998999375 } } } } } } }, "UnityEnvironment.step": { "total": 1361.3673293910356, "count": 63728, "is_parallel": true, "self": 35.57708939598365, "children": { "UnityEnvironment._generate_step_input": { "total": 25.70883990007087, "count": 63728, "is_parallel": true, "self": 25.70883990007087 }, "communicator.exchange": { "total": 1193.677246763014, "count": 63728, "is_parallel": true, "self": 1193.677246763014 }, "steps_from_proto": { "total": 106.40415333196711, "count": 63728, "is_parallel": true, "self": 22.221382584804587, "children": { "_process_rank_one_or_two_observation": { "total": 84.18277074716252, "count": 509824, "is_parallel": true, "self": 84.18277074716252 } } } } } } } } } } }, "trainer_advance": { "total": 623.9482953920526, "count": 63729, "self": 2.9352461930368463, "children": { "process_trajectory": { "total": 131.0062470710127, "count": 63729, "self": 130.7327684670131, "children": { "RLTrainer._checkpoint": { "total": 0.27347860399959245, "count": 2, "self": 0.27347860399959245 } } }, "_update_policy": { "total": 490.0068021280031, "count": 449, "self": 286.6264814439619, "children": { "TorchPPOOptimizer.update": { "total": 203.38032068404118, "count": 22785, "self": 203.38032068404118 } } } } } } }, "trainer_threads": { "total": 1.3849999049853068e-06, "count": 1, "self": 1.3849999049853068e-06 }, "TrainerController._save_models": { "total": 0.09520810599997276, "count": 1, "self": 0.001586349999797676, "children": { "RLTrainer._checkpoint": { "total": 0.09362175600017508, "count": 1, "self": 0.09362175600017508 } } } } } } }